metadata
license: apache-2.0
language:
- zh
- en
base_model:
- Qwen/Qwen3-4B
tags:
- onnx
- foundry-local
- directml
- dml
- int4
- windows
Converted Qwen3-4B to ONNX Runtime GenAI format for use in Foundry Local inference.
This commit includes:
ONNX model artifacts (model.onnx / model.onnx.data) tokenizer and runtime configs (tokenizer.json, tokenizer_config.json, genai_config.json) chat and prompt templates (chat_template.jinja, inference_model.json) Conversion settings:
Quantization: INT4 Target execution provider: DirectML (DML) Target platform: Windows + Foundry Local